用翻译模型改进英越词对齐

2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future Pub Date : 2012-03-15 DOI:10.1109/rivf.2012.6169841

Giang Nguyen, Dinh Dien

{"title":"用翻译模型改进英越词对齐","authors":"Giang Nguyen, Dinh Dien","doi":"10.1109/rivf.2012.6169841","DOIUrl":null,"url":null,"abstract":"Word alignment for a parallel corpus is the connection between the words/phrases in source language and the words/phrases in target language. The alignment result is an important input for many natural language processing applications. In this paper, we propose an approach to improve the English-Vietnamese word alignment result by using the alignment frequency that is presented in the translation model of SMT (Statistical Machine Translation). We also indicate 5 common error types of English-Vietnamese word alignment and propose the heuristic patterns to discover the alignment errors. The experimental results show the improvement compared to the result of GIZA++.","PeriodicalId":115212,"journal":{"name":"2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Improving English-Vietnamese Word Alignment Using Translation Model\",\"authors\":\"Giang Nguyen, Dinh Dien\",\"doi\":\"10.1109/rivf.2012.6169841\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Word alignment for a parallel corpus is the connection between the words/phrases in source language and the words/phrases in target language. The alignment result is an important input for many natural language processing applications. In this paper, we propose an approach to improve the English-Vietnamese word alignment result by using the alignment frequency that is presented in the translation model of SMT (Statistical Machine Translation). We also indicate 5 common error types of English-Vietnamese word alignment and propose the heuristic patterns to discover the alignment errors. The experimental results show the improvement compared to the result of GIZA++.\",\"PeriodicalId\":115212,\"journal\":{\"name\":\"2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2012-03-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/rivf.2012.6169841\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/rivf.2012.6169841","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

平行语料库中的词对齐是指源语言中的词/短语与目标语言中的词/短语之间的连接。对齐结果是许多自然语言处理应用程序的重要输入。在本文中，我们提出了一种利用统计机器翻译(SMT)翻译模型中提供的对齐频率来改善英越词对齐结果的方法。我们还指出了英汉越词对齐中常见的5种错误类型，并提出了发现英汉越词对齐错误的启发式模式。实验结果表明，与giz++的结果相比，该方法有很大的改进。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Improving English-Vietnamese Word Alignment Using Translation Model

Word alignment for a parallel corpus is the connection between the words/phrases in source language and the words/phrases in target language. The alignment result is an important input for many natural language processing applications. In this paper, we propose an approach to improve the English-Vietnamese word alignment result by using the alignment frequency that is presented in the translation model of SMT (Statistical Machine Translation). We also indicate 5 common error types of English-Vietnamese word alignment and propose the heuristic patterns to discover the alignment errors. The experimental results show the improvement compared to the result of GIZA++.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future

自引率

0.00%

发文量